Abstract
The graph-to-sequence (Graph2Seq) learning aims to transduce graph-structured representations to word sequences for text generation. Recent studies propose various models to encode graph structure. However, most previous works ignore the indirect relations between distance nodes, or treat indirect relations and direct relations in the same way. In this paper, we propose the Heterogeneous Graph Transformer to independently model the different relations in the individual subgraphs of the original graph, including direct relations, indirect relations and multiple possible relations between nodes. Experimental results show that our model strongly outperforms the state of the art on all four standard benchmarks of AMR-to-text generation and syntax-based neural machine translation.- Anthology ID:
- 2020.acl-main.640
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7145–7154
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.640
- DOI:
- 10.18653/v1/2020.acl-main.640
- Cite (ACL):
- Shaowei Yao, Tianming Wang, and Xiaojun Wan. 2020. Heterogeneous Graph Transformer for Graph-to-Sequence Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7145–7154, Online. Association for Computational Linguistics.
- Cite (Informal):
- Heterogeneous Graph Transformer for Graph-to-Sequence Learning (Yao et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.640.pdf